Methods › Audio › Text-to-Speech Models › Deep Voice 3
Deep Voice 3
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Deep Voice 3 (DV3) is a fully-convolutional attention-based neural text-to-speech system. The Deep Voice 3 architecture consists of three components:
-
Encoder: A fully-convolutional encoder, which converts textual features to an internal learned representation.
-
Decoder: A fully-convolutional causal decoder, which decodes the learned representation with a multi-hop convolutional attention mechanism into a low-dimensional audio representation (mel-scale spectrograms) in an autoregressive manner.
-
Converter: A fully-convolutional post-processing network, which predicts final vocoder parameters (depending on the vocoder choice) from the decoder hidden states. Unlike the decoder, the converter is non-causal and can thus depend on future context information.
The overall objective function to be optimized is a linear combination of the losses from the decoder and the converter. The authors separate decoder and converter and apply multi-task training, because it makes attention learning easier in practice. To be specific, the loss for mel-spectrogram prediction guides training of the attention mechanism, because the attention is trained with the gradients from mel-spectrogram prediction besides vocoder parameter prediction.
In Syntology name not resolved (unknown_name). Other entries in Syntology's graph carry this name; the lookup's note below says what that means for this name.
From the lookup's note on this name: Nothing resolved to this name, but 2 entries in Syntology's graph carry it; the most cited is the paper “Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning” (arXiv:1710.07654, 322 citations). The lookup reads this as a miss of its own name matching, not a gap in coverage: the graph holds the name under a spelling the lookup did not reach. For arXiv:1710.07654: its page on this site · ask the lookup about it.
Near matches the lookup lists, each a different name: VoICE; Saar-Voice; Auden-voice; Praxy Voice; Voice Memory; Voice of India; Zero-Shot Voice Cloning; Pashto Common Voice corpus.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 3 · with a code link: 2 · where Syntology ran a sample: 2 (1 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (2 of 3 tagged: 1 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 3 of 3, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
Parallel Neural Text-to-Speech 1 Jan 2020 · 0 repositories
-
Non-Autoregressive Neural Text-to-Speech 21 May 2019 · 2 repositories · arXiv:1905.08459Syntology 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples)
-
Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning 20 Oct 2017 · 7 repositories · arXiv:1710.07654Syntology 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
Tasks archive 2025-07-28
5 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Text to Speech | 3 |
| text-to-speech | 3 |
| GPU | 1 |
| Speech Synthesis | 1 |
| Text-To-Speech Synthesis | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections